Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0589. Min Act: -0.0001

Data Index: 122850 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0128. Min Act: -0.0001

Data Index: 1079732 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0082. Min Act: -0.0001

Data Index: 601071 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.0589. Min Range: -1.0589

Max Act: 1.0003. Min Act: -0.0001

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9372. Min Act: -0.0001

Data Index: 173458 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9406. Min Act: -0.0001

Data Index: 1157337 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9381. Min Act: -0.0001

Data Index: 1326436 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8607. Min Act: -0.0001

Data Index: 753253 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9035. Min Act: -0.0001

Data Index: 392142 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8931. Min Act: -0.0001

Data Index: 287700 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1188852 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9119. Min Act: -0.0001

Data Index: 952524 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1139435 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7987. Min Act: -0.0001

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8495. Min Act: -0.0001

Data Index: 990334 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8334. Min Act: -0.0001

Data Index: 1326830 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8019. Min Act: -0.0001

Data Index: 705870 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8182. Min Act: -0.0001

Data Index: 537689 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1012536 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.0589. Min Range: -1.0589

Max Act: 0.8027. Min Act: -0.0000

Data Index: 403243 (C4 (Web Text))

Max Activating Token Index: 192